--- license: apache-2.0 library_name: peft tags: - axolotl - generated_from_trainer base_model: unsloth/Qwen2.5-Math-7B-Instruct model-index: - name: 5660f73b-66a5-48c0-89ba-03bbcd40fe2c results: [] --- [Built with Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl)
See axolotl config axolotl version: `0.4.1` ```yaml adapter: lora base_model: unsloth/Qwen2.5-Math-7B-Instruct bf16: auto dataset_prepared_path: null datasets: - data_files: - 773d8cd61dad3eec_train_data.json ds_type: json format: custom path: 773d8cd61dad3eec_train_data.json type: field: null field_input: null field_instruction: instruction field_output: output_1 field_system: null format: null no_input_format: null system_format: '{system}' system_prompt: '' debug: null deepspeed: null early_stopping_patience: null eval_max_new_tokens: 128 eval_table_size: null evals_per_epoch: 2 flash_attention: null fp16: null fsdp: null fsdp_config: null gradient_accumulation_steps: 4 gradient_checkpointing: false group_by_length: false hub_model_id: taopanda/5660f73b-66a5-48c0-89ba-03bbcd40fe2c learning_rate: 0.0002 load_in_4bit: false load_in_8bit: true local_rank: null logging_steps: 1 lora_alpha: 16 lora_dropout: 0.05 lora_fan_in_fan_out: null lora_model_dir: null lora_r: 32 lora_target_linear: true lr_scheduler: cosine micro_batch_size: 2 model_type: AutoModelForCausalLM num_epochs: 2 optimizer: adamw_bnb_8bit output_dir: ./outputs/lora-out/taopanda-4_e59ee620-6dc6-41b8-8080-617c8e470bc7 pad_to_sequence_len: null resume_from_checkpoint: null sample_packing: false saves_per_epoch: 1 seed: 71158 sequence_len: 2048 special_tokens: null strict: false tf32: false tokenizer_type: AutoTokenizer train_on_inputs: false trust_remote_code: true val_set_size: 0.05 wandb_entity: fatcat87-taopanda wandb_log_model: null wandb_mode: online wandb_name: taopanda-4_e59ee620-6dc6-41b8-8080-617c8e470bc7 wandb_project: subnet56 wandb_runid: taopanda-4_e59ee620-6dc6-41b8-8080-617c8e470bc7 wandb_watch: null warmup_steps: 10 weight_decay: 0.0 xformers_attention: null ```

[Visualize in Weights & Biases](https://wandb.ai/fatcat87-taopanda/subnet56/runs/xe0o87ef) # 5660f73b-66a5-48c0-89ba-03bbcd40fe2c This model is a fine-tuned version of [unsloth/Qwen2.5-Math-7B-Instruct](https://huggingface.co/unsloth/Qwen2.5-Math-7B-Instruct) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.6838 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0002 - train_batch_size: 2 - eval_batch_size: 2 - seed: 71158 - distributed_type: multi-GPU - num_devices: 4 - gradient_accumulation_steps: 4 - total_train_batch_size: 32 - total_eval_batch_size: 8 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 10 - num_epochs: 2 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:------:|:----:|:---------------:| | 2.6733 | 0.0020 | 1 | 2.6805 | | 1.6576 | 0.4997 | 245 | 1.8743 | | 1.7399 | 0.9995 | 490 | 1.7528 | | 1.6637 | 1.4992 | 735 | 1.6954 | | 1.6485 | 1.9990 | 980 | 1.6838 | ### Framework versions - PEFT 0.11.1 - Transformers 4.42.3 - Pytorch 2.3.0+cu121 - Datasets 2.19.1 - Tokenizers 0.19.1